Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +1 -1
- config.json +15 -3
- generation_config.json +1 -1
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- en
|
4 |
license: apache-2.0
|
@@ -9,7 +10,6 @@ tags:
|
|
9 |
- qwen2
|
10 |
- trl
|
11 |
- sft
|
12 |
-
base_model: unsloth/Qwen2-1.5B-Instruct
|
13 |
---
|
14 |
|
15 |
# Uploaded model
|
|
|
1 |
---
|
2 |
+
base_model: unsloth/Qwen2-1.5B-Instruct
|
3 |
language:
|
4 |
- en
|
5 |
license: apache-2.0
|
|
|
10 |
- qwen2
|
11 |
- trl
|
12 |
- sft
|
|
|
13 |
---
|
14 |
|
15 |
# Uploaded model
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "unsloth/
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
@@ -16,13 +16,25 @@
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 28,
|
18 |
"num_key_value_heads": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_theta": 1000000.0,
|
21 |
"sliding_window": 32768,
|
22 |
"tie_word_embeddings": true,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
-
"transformers_version": "4.
|
25 |
-
"unsloth_version": "2024.
|
26 |
"use_cache": true,
|
27 |
"use_sliding_window": false,
|
28 |
"vocab_size": 151936
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/qwen2-1.5b-instruct-bnb-4bit",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 28,
|
18 |
"num_key_value_heads": 2,
|
19 |
+
"quantization_config": {
|
20 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
21 |
+
"bnb_4bit_quant_type": "nf4",
|
22 |
+
"bnb_4bit_use_double_quant": true,
|
23 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
24 |
+
"llm_int8_has_fp16_weight": false,
|
25 |
+
"llm_int8_skip_modules": null,
|
26 |
+
"llm_int8_threshold": 6.0,
|
27 |
+
"load_in_4bit": true,
|
28 |
+
"load_in_8bit": false,
|
29 |
+
"quant_method": "bitsandbytes"
|
30 |
+
},
|
31 |
"rms_norm_eps": 1e-06,
|
32 |
"rope_theta": 1000000.0,
|
33 |
"sliding_window": 32768,
|
34 |
"tie_word_embeddings": true,
|
35 |
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.41.2",
|
37 |
+
"unsloth_version": "2024.6",
|
38 |
"use_cache": true,
|
39 |
"use_sliding_window": false,
|
40 |
"vocab_size": 151936
|
generation_config.json
CHANGED
@@ -10,5 +10,5 @@
|
|
10 |
"temperature": 0.7,
|
11 |
"top_k": 20,
|
12 |
"top_p": 0.8,
|
13 |
-
"transformers_version": "4.
|
14 |
}
|
|
|
10 |
"temperature": 0.7,
|
11 |
"top_k": 20,
|
12 |
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.41.2"
|
14 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa1f1630ad69cca0022e8c1089997e443c162a79ecd25a5e2716e41eecc4a09
|
3 |
+
size 1217251687
|